© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 5023
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing composure and maintaining grace under pressure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onOptions
    -0.53
     dirty
    -0.52
     Dirty
    -0.51
     Vikipedi
    -0.51
    Dirty
    -0.51
     want
    -0.50
     wanting
    -0.50
    Autoritní
    -0.50
     dag
    -0.49
    want
    -0.49
    POSITIVE LOGITS
     composure
    0.73
     calmness
    0.69
     Exacts
    0.66
     calmly
    0.66
     Calm
    0.64
    Calm
    0.64
     calme
    0.64
     zelve
    0.61
     quæ
    0.61
     calm
    0.59
    Activations Density 0.230%

    No Known Activations